Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 720 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.6603. Min Act: -0.0000

Data Index: 939252 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.8188. Min Act: -0.0000

Data Index: 506710 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.7164. Min Act: -0.0000

Data Index: 1453919 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.2434. Min Act: -0.0000

Data Index: 517915 (The Pile)

Max Activating Token Index: 656

Text #4

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.3546. Min Act: -0.0000

Data Index: 1462253 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.2910. Min Act: -0.0000

Data Index: 139075 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.3103. Min Act: -0.0000

Data Index: 1929776 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.2981. Min Act: -0.0000

Data Index: 1932975 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4497. Min Act: -0.0000

Data Index: 908227 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.2872. Min Act: -0.0000

Data Index: 1887294 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.2639. Min Act: -0.0000

Data Index: 263768 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 3.8188. Min Range: -3.8188

Max Act: 2.9490. Min Act: -0.0000

Data Index: 344170 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4824. Min Act: -0.0000

Data Index: 127284 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 3.8188. Min Range: -3.8188

Max Act: 2.9083. Min Act: -0.0000

Data Index: 1166792 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4979. Min Act: -0.0000

Data Index: 1722899 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.2780. Min Act: -0.0000

Data Index: 1971086 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.1204. Min Act: -0.0000

Data Index: 1869758 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 3.8188. Min Range: -3.8188

Max Act: 2.9869. Min Act: -0.0000

Data Index: 1272013 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 3.8188. Min Range: -3.8188

Max Act: 2.9987. Min Act: -0.0001

Data Index: 1285001 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.2330. Min Act: -0.0000

Data Index: 1611525 (The Pile)

Max Activating Token Index: 570